The patch titled introduce "struct wait_opts" to simplify do_wait() patches has been added to the -mm tree. Its filename is introduce-struct-wait_opts-to-simplify-do_wait-pathes.patch Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/SubmitChecklist when testing your code *** See http://userweb.kernel.org/~akpm/stuff/added-to-mm.txt to find out what to do about this The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/ ------------------------------------------------------ Subject: introduce "struct wait_opts" to simplify do_wait() patches From: Oleg Nesterov <oleg@xxxxxxxxxx> Introduce "struct wait_opts" which holds the parameters for misc helpers in do_wait() pathes. This adds 13 lines to kernel/exit.c, but saves 256 bytes from .o and imho makes the code much more readable. This patch temporary uglifies rusage/siginfo code a little bit, will be addressed by further cleanups. Signed-off-by: Oleg Nesterov <oleg@xxxxxxxxxx> Reviewed-by: Ingo Molnar <mingo@xxxxxxx> Acked-by: Roland McGrath <roland@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- kernel/exit.c | 209 +++++++++++++++++++++++++----------------------- 1 file changed, 111 insertions(+), 98 deletions(-) diff -puN kernel/exit.c~introduce-struct-wait_opts-to-simplify-do_wait-pathes kernel/exit.c --- a/kernel/exit.c~introduce-struct-wait_opts-to-simplify-do_wait-pathes +++ a/kernel/exit.c @@ -1078,6 +1078,18 @@ SYSCALL_DEFINE1(exit_group, int, error_c return 0; } +struct wait_opts { + enum pid_type wo_type; + struct pid *wo_pid; + int wo_flags; + + struct siginfo __user *wo_info; + int __user *wo_stat; + struct rusage __user *wo_rusage; + + int notask_error; +}; + static struct pid *task_pid_type(struct task_struct *task, enum pid_type type) { struct pid *pid = NULL; @@ -1088,13 +1100,12 @@ static struct pid *task_pid_type(struct return pid; } -static int eligible_child(enum pid_type type, struct pid *pid, int options, - struct task_struct *p) +static int eligible_child(struct wait_opts *wo, struct task_struct *p) { int err; - if (type < PIDTYPE_MAX) { - if (task_pid_type(p, type) != pid) + if (wo->wo_type < PIDTYPE_MAX) { + if (task_pid_type(p, wo->wo_type) != wo->wo_pid) return 0; } @@ -1103,8 +1114,8 @@ static int eligible_child(enum pid_type * set; otherwise, wait for non-clone children *only*. (Note: * A "clone" child here is one that reports to its parent * using a signal other than SIGCHLD.) */ - if (((p->exit_signal != SIGCHLD) ^ ((options & __WCLONE) != 0)) - && !(options & __WALL)) + if (((p->exit_signal != SIGCHLD) ^ !!(wo->wo_flags & __WCLONE)) + && !(wo->wo_flags & __WALL)) return 0; err = security_task_wait(p); @@ -1114,14 +1125,15 @@ static int eligible_child(enum pid_type return 1; } -static int wait_noreap_copyout(struct task_struct *p, pid_t pid, uid_t uid, - int why, int status, - struct siginfo __user *infop, - struct rusage __user *rusagep) +static int wait_noreap_copyout(struct wait_opts *wo, struct task_struct *p, + pid_t pid, uid_t uid, int why, int status) { - int retval = rusagep ? getrusage(p, RUSAGE_BOTH, rusagep) : 0; + struct siginfo __user *infop; + int retval = wo->wo_rusage + ? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0; put_task_struct(p); + infop = wo->wo_info; if (!retval) retval = put_user(SIGCHLD, &infop->si_signo); if (!retval) @@ -1145,19 +1157,18 @@ static int wait_noreap_copyout(struct ta * the lock and this task is uninteresting. If we return nonzero, we have * released the lock and the system call should return. */ -static int wait_task_zombie(struct task_struct *p, int options, - struct siginfo __user *infop, - int __user *stat_addr, struct rusage __user *ru) +static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) { unsigned long state; int retval, status, traced; pid_t pid = task_pid_vnr(p); uid_t uid = __task_cred(p)->uid; + struct siginfo __user *infop; - if (!likely(options & WEXITED)) + if (!likely(wo->wo_flags & WEXITED)) return 0; - if (unlikely(options & WNOWAIT)) { + if (unlikely(wo->wo_flags & WNOWAIT)) { int exit_code = p->exit_code; int why, status; @@ -1170,8 +1181,7 @@ static int wait_task_zombie(struct task_ why = (exit_code & 0x80) ? CLD_DUMPED : CLD_KILLED; status = exit_code & 0x7f; } - return wait_noreap_copyout(p, pid, uid, why, - status, infop, ru); + return wait_noreap_copyout(wo, p, pid, uid, why, status); } /* @@ -1256,11 +1266,14 @@ static int wait_task_zombie(struct task_ */ read_unlock(&tasklist_lock); - retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0; + retval = wo->wo_rusage + ? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0; status = (p->signal->flags & SIGNAL_GROUP_EXIT) ? p->signal->group_exit_code : p->exit_code; - if (!retval && stat_addr) - retval = put_user(status, stat_addr); + if (!retval && wo->wo_stat) + retval = put_user(status, wo->wo_stat); + + infop = wo->wo_info; if (!retval && infop) retval = put_user(SIGCHLD, &infop->si_signo); if (!retval && infop) @@ -1328,10 +1341,10 @@ static int *task_stopped_code(struct tas * the lock and this task is uninteresting. If we return nonzero, we have * released the lock and the system call should return. */ -static int wait_task_stopped(int ptrace, struct task_struct *p, - int options, struct siginfo __user *infop, - int __user *stat_addr, struct rusage __user *ru) +static int wait_task_stopped(struct wait_opts *wo, + int ptrace, struct task_struct *p) { + struct siginfo __user *infop; int retval, exit_code, *p_code, why; uid_t uid = 0; /* unneeded, required by compiler */ pid_t pid; @@ -1339,7 +1352,7 @@ static int wait_task_stopped(int ptrace, /* * Traditionally we see ptrace'd stopped tasks regardless of options. */ - if (!ptrace && !(options & WUNTRACED)) + if (!ptrace && !(wo->wo_flags & WUNTRACED)) return 0; exit_code = 0; @@ -1353,7 +1366,7 @@ static int wait_task_stopped(int ptrace, if (!exit_code) goto unlock_sig; - if (!unlikely(options & WNOWAIT)) + if (!unlikely(wo->wo_flags & WNOWAIT)) *p_code = 0; /* don't need the RCU readlock here as we're holding a spinlock */ @@ -1375,14 +1388,15 @@ unlock_sig: why = ptrace ? CLD_TRAPPED : CLD_STOPPED; read_unlock(&tasklist_lock); - if (unlikely(options & WNOWAIT)) - return wait_noreap_copyout(p, pid, uid, - why, exit_code, - infop, ru); - - retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0; - if (!retval && stat_addr) - retval = put_user((exit_code << 8) | 0x7f, stat_addr); + if (unlikely(wo->wo_flags & WNOWAIT)) + return wait_noreap_copyout(wo, p, pid, uid, why, exit_code); + + retval = wo->wo_rusage + ? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0; + if (!retval && wo->wo_stat) + retval = put_user((exit_code << 8) | 0x7f, wo->wo_stat); + + infop = wo->wo_info; if (!retval && infop) retval = put_user(SIGCHLD, &infop->si_signo); if (!retval && infop) @@ -1409,15 +1423,13 @@ unlock_sig: * the lock and this task is uninteresting. If we return nonzero, we have * released the lock and the system call should return. */ -static int wait_task_continued(struct task_struct *p, int options, - struct siginfo __user *infop, - int __user *stat_addr, struct rusage __user *ru) +static int wait_task_continued(struct wait_opts *wo, struct task_struct *p) { int retval; pid_t pid; uid_t uid; - if (!unlikely(options & WCONTINUED)) + if (!unlikely(wo->wo_flags & WCONTINUED)) return 0; if (!(p->signal->flags & SIGNAL_STOP_CONTINUED)) @@ -1429,7 +1441,7 @@ static int wait_task_continued(struct ta spin_unlock_irq(&p->sighand->siglock); return 0; } - if (!unlikely(options & WNOWAIT)) + if (!unlikely(wo->wo_flags & WNOWAIT)) p->signal->flags &= ~SIGNAL_STOP_CONTINUED; uid = __task_cred(p)->uid; spin_unlock_irq(&p->sighand->siglock); @@ -1438,17 +1450,17 @@ static int wait_task_continued(struct ta get_task_struct(p); read_unlock(&tasklist_lock); - if (!infop) { - retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0; + if (!wo->wo_info) { + retval = wo->wo_rusage + ? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0; put_task_struct(p); - if (!retval && stat_addr) - retval = put_user(0xffff, stat_addr); + if (!retval && wo->wo_stat) + retval = put_user(0xffff, wo->wo_stat); if (!retval) retval = pid; } else { - retval = wait_noreap_copyout(p, pid, uid, - CLD_CONTINUED, SIGCONT, - infop, ru); + retval = wait_noreap_copyout(wo, p, pid, uid, + CLD_CONTINUED, SIGCONT); BUG_ON(retval == 0); } @@ -1458,19 +1470,16 @@ static int wait_task_continued(struct ta /* * Consider @p for a wait by @parent. * - * -ECHILD should be in *@notask_error before the first call. + * -ECHILD should be in ->notask_error before the first call. * Returns nonzero for a final return, when we have unlocked tasklist_lock. * Returns zero if the search for a child should continue; - * then *@notask_error is 0 if @p is an eligible child, + * then ->notask_error is 0 if @p is an eligible child, * or another error from security_task_wait(), or still -ECHILD. */ -static int wait_consider_task(struct task_struct *parent, int ptrace, - struct task_struct *p, int *notask_error, - enum pid_type type, struct pid *pid, int options, - struct siginfo __user *infop, - int __user *stat_addr, struct rusage __user *ru) +static int wait_consider_task(struct wait_opts *wo, struct task_struct *parent, + int ptrace, struct task_struct *p) { - int ret = eligible_child(type, pid, options, p); + int ret = eligible_child(wo, p); if (!ret) return ret; @@ -1482,8 +1491,8 @@ static int wait_consider_task(struct tas * to look for security policy problems, rather * than for mysterious wait bugs. */ - if (*notask_error) - *notask_error = ret; + if (wo->notask_error) + wo->notask_error = ret; return 0; } @@ -1492,7 +1501,7 @@ static int wait_consider_task(struct tas * This child is hidden by ptrace. * We aren't allowed to see it now, but eventually we will. */ - *notask_error = 0; + wo->notask_error = 0; return 0; } @@ -1503,34 +1512,30 @@ static int wait_consider_task(struct tas * We don't reap group leaders with subthreads. */ if (p->exit_state == EXIT_ZOMBIE && !delay_group_leader(p)) - return wait_task_zombie(p, options, infop, stat_addr, ru); + return wait_task_zombie(wo, p); /* * It's stopped or running now, so it might * later continue, exit, or stop again. */ - *notask_error = 0; + wo->notask_error = 0; if (task_stopped_code(p, ptrace)) - return wait_task_stopped(ptrace, p, options, - infop, stat_addr, ru); + return wait_task_stopped(wo, ptrace, p); - return wait_task_continued(p, options, infop, stat_addr, ru); + return wait_task_continued(wo, p); } /* * Do the work of do_wait() for one thread in the group, @tsk. * - * -ECHILD should be in *@notask_error before the first call. + * -ECHILD should be in ->notask_error before the first call. * Returns nonzero for a final return, when we have unlocked tasklist_lock. * Returns zero if the search for a child should continue; then - * *@notask_error is 0 if there were any eligible children, + * ->notask_error is 0 if there were any eligible children, * or another error from security_task_wait(), or still -ECHILD. */ -static int do_wait_thread(struct task_struct *tsk, int *notask_error, - enum pid_type type, struct pid *pid, int options, - struct siginfo __user *infop, int __user *stat_addr, - struct rusage __user *ru) +static int do_wait_thread(struct wait_opts *wo, struct task_struct *tsk) { struct task_struct *p; @@ -1539,9 +1544,7 @@ static int do_wait_thread(struct task_st * Do not consider detached threads. */ if (!task_detached(p)) { - int ret = wait_consider_task(tsk, 0, p, notask_error, - type, pid, options, - infop, stat_addr, ru); + int ret = wait_consider_task(wo, tsk, 0, p); if (ret) return ret; } @@ -1550,17 +1553,12 @@ static int do_wait_thread(struct task_st return 0; } -static int ptrace_do_wait(struct task_struct *tsk, int *notask_error, - enum pid_type type, struct pid *pid, int options, - struct siginfo __user *infop, int __user *stat_addr, - struct rusage __user *ru) +static int ptrace_do_wait(struct wait_opts *wo, struct task_struct *tsk) { struct task_struct *p; list_for_each_entry(p, &tsk->ptraced, ptrace_entry) { - int ret = wait_consider_task(tsk, 1, p, notask_error, - type, pid, options, - infop, stat_addr, ru); + int ret = wait_consider_task(wo, tsk, 1, p); if (ret) return ret; } @@ -1568,38 +1566,36 @@ static int ptrace_do_wait(struct task_st return 0; } -static long do_wait(enum pid_type type, struct pid *pid, int options, - struct siginfo __user *infop, int __user *stat_addr, - struct rusage __user *ru) +static long do_wait(struct wait_opts *wo) { DECLARE_WAITQUEUE(wait, current); struct task_struct *tsk; int retval; - trace_sched_process_wait(pid); + trace_sched_process_wait(wo->wo_pid); add_wait_queue(¤t->signal->wait_chldexit,&wait); repeat: /* * If there is nothing that can match our critiera just get out. - * We will clear @retval to zero if we see any child that might later - * match our criteria, even if we are not able to reap it yet. + * We will clear ->notask_error to zero if we see any child that + * might later match our criteria, even if we are not able to reap + * it yet. */ - retval = -ECHILD; - if ((type < PIDTYPE_MAX) && (!pid || hlist_empty(&pid->tasks[type]))) + retval = wo->notask_error = -ECHILD; + if ((wo->wo_type < PIDTYPE_MAX) && + (!wo->wo_pid || hlist_empty(&wo->wo_pid->tasks[wo->wo_type]))) goto end; current->state = TASK_INTERRUPTIBLE; read_lock(&tasklist_lock); tsk = current; do { - int tsk_result = do_wait_thread(tsk, &retval, - type, pid, options, - infop, stat_addr, ru); + int tsk_result = do_wait_thread(wo, tsk); + if (!tsk_result) - tsk_result = ptrace_do_wait(tsk, &retval, - type, pid, options, - infop, stat_addr, ru); + tsk_result = ptrace_do_wait(wo, tsk); + if (tsk_result) { /* * tasklist_lock is unlocked and we have a final result. @@ -1608,25 +1604,27 @@ repeat: goto end; } - if (options & __WNOTHREAD) + if (wo->wo_flags & __WNOTHREAD) break; tsk = next_thread(tsk); BUG_ON(tsk->signal != current->signal); } while (tsk != current); read_unlock(&tasklist_lock); - if (!retval && !(options & WNOHANG)) { + retval = wo->notask_error; + if (!retval && !(wo->wo_flags & WNOHANG)) { retval = -ERESTARTSYS; if (!signal_pending(current)) { schedule(); goto repeat; } } - end: current->state = TASK_RUNNING; remove_wait_queue(¤t->signal->wait_chldexit,&wait); - if (infop) { + if (wo->wo_info) { + struct siginfo __user *infop = wo->wo_info; + if (retval > 0) retval = 0; else { @@ -1655,6 +1653,7 @@ end: SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *, infop, int, options, struct rusage __user *, ru) { + struct wait_opts wo; struct pid *pid = NULL; enum pid_type type; long ret; @@ -1684,7 +1683,14 @@ SYSCALL_DEFINE5(waitid, int, which, pid_ if (type < PIDTYPE_MAX) pid = find_get_pid(upid); - ret = do_wait(type, pid, options, infop, NULL, ru); + + wo.wo_type = type; + wo.wo_pid = pid; + wo.wo_flags = options; + wo.wo_info = infop; + wo.wo_stat = NULL; + wo.wo_rusage = ru; + ret = do_wait(&wo); put_pid(pid); /* avoid REGPARM breakage on x86: */ @@ -1695,6 +1701,7 @@ SYSCALL_DEFINE5(waitid, int, which, pid_ SYSCALL_DEFINE4(wait4, pid_t, upid, int __user *, stat_addr, int, options, struct rusage __user *, ru) { + struct wait_opts wo; struct pid *pid = NULL; enum pid_type type; long ret; @@ -1716,7 +1723,13 @@ SYSCALL_DEFINE4(wait4, pid_t, upid, int pid = find_get_pid(upid); } - ret = do_wait(type, pid, options | WEXITED, NULL, stat_addr, ru); + wo.wo_type = type; + wo.wo_pid = pid; + wo.wo_flags = options | WEXITED; + wo.wo_info = NULL; + wo.wo_stat = stat_addr; + wo.wo_rusage = ru; + ret = do_wait(&wo); put_pid(pid); /* avoid REGPARM breakage on x86: */ _ Patches currently in -mm which might be from oleg@xxxxxxxxxx are origin.patch linux-next.patch drivers-staging-epl-do-not-use-clone_sighand-with-allow_signal.patch slow_work_thread-should-do-the-exclusive-wait.patch rework-fix-is_single_threaded.patch getrusage-fill-ru_maxrss-value.patch allow_signal-kill-the-bogus-mm-check-add-a-note-about-clone_sighand.patch ptrace-remove-pt_dtrace-from-arch-h8300.patch ptrace-remove-pt_dtrace-from-avr32-mn10300-parisc-s390-sh-xtensa.patch ptrace-remove-pt_dtrace-from-m68k-m68knommu.patch ptrace-remove-pt_dtrace-from-arch-m32r.patch ptrace-mm_need_new_owner-use-real_parent-to-search-in-the-siblings.patch ptrace-tracehook_unsafe_exec-remove-the-stale-comment.patch ptrace-tracehook_unsafe_exec-remove-the-stale-comment-fix.patch ptrace-do-not-use-task-ptrace-directly-in-core-kernel.patch ptrace-ptrace_attach-check-pf_kthread-exit_state-instead-of-mm.patch ptrace-cleanup-check-set-of-pt_ptraced-during-attach.patch ptrace-do-not-use-task_lock-for-attach.patch ptrace_get_task_struct-s-tasklist-rcu-make-it-static.patch signals-tracehook_notify_jctl-change.patch utrace-core.patch copy_process-remove-the-unneeded-clear_tsk_thread_flagtif_sigpending.patch elf_core_dump-use-rcu_read_lock-to-access-real_parent.patch shift-ptrace-implies-wuntraced-from-ptrace_do_wait-to-wait_task_stopped.patch introduce-struct-wait_opts-to-simplify-do_wait-pathes.patch do_wait-simplify-retval-tsk_result-notask_error-mess.patch do_wait-kill-the-old-bug_on-use-while_each_thread.patch do_wait-fix-the-theoretical-race-with-stop-trace-cont.patch kthreads-simplify-the-startup-synchronization.patch kthreads-rework-kthread_stop.patch kthreads-simplify-migration_thread-exit-path.patch -- To unsubscribe from this list: send the line "unsubscribe mm-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html